Free-LLM Router · free & open source

All the free AI APIs.
One address. Never stuck.

Run Claude Code, Codex, Cursor, Aider or your own app on 350+ free models from 66 providers. When one free plan runs out, the router switches to the next one — instantly.

$ curl -fsSL https://free-llm.com/install.sh | sh

macOS · Linux · Windows, npm & Docker · needs Node.js 18+

The idea, in plain words

Dozens of companies give AI away for free. But each free plan is small — a few requests per minute, a daily cap — and each has its own key, own address and own rules. When one runs out in the middle of your work, your tool simply stops.

1

Your app talks to one address

Claude Code, Cursor or your script sends a normal OpenAI- or Anthropic-style request to localhost:4000.

2

The router picks a free model

The best one that is up right now — by quality, speed and quota left. It learns from every answer.

3

Busy? Next one. Instantly.

Rate limit, daily quota, error or silence: it switches to another free model before your app notices.

 Claude Code · Codex · Cursor · your app
                   │   one address, one key
                   ▼
         ⚡ Free-LLM Router  (on your computer)
      ┌──────┬──────┬────────┬──────────┬────────┐
      ▼      ▼      ▼        ▼          ▼        ▼
   Gemini  Groq  Mistral  OpenRouter  NVIDIA  …61 more

The big advantage

Many small free plans, stacked together, behave like one big free plan — that doesn't go down.

66

free providers it can use

350+

free models

25

need no credit card

$0

no premium tier, ever

Numbers are live from the free-llm.com directory. New free model this morning? It reaches every router the same day.

Install in one minute

It starts a short guided setup: it shows the best free providers, you paste a key or two, it tests them, and it can configure your coding tools for you. Then open http://localhost:4000.

curl -fsSL https://free-llm.com/install.sh | sh

No admin rights, nothing global: installs into ~/.free-llm and adds a `free-llm` command.

🚀 Works with zero keys

Guest mode answers right away (slow, limited) so you can see it work before signing up anywhere.

🔑 Then add 2–3 free keys

Google AI Studio, Groq, OpenRouter… about a minute each, most without a credit card.

🖥️ Dashboard included

Add and test keys, see which models are ready, chat playground, live activity, settings.

Works with 22 tools out of the box

Coding agents are configured with one command (your previous settings are backed up, --remove undoes it). Everything else gets a copy-paste recipe in the dashboard.

Claude Code

free-llm setup claude

Codex CLI

free-llm setup codex

OpenCode

free-llm setup opencode

Aider

free-llm setup aider

Qwen Code

free-llm launch qwen

Goose

free-llm launch goose

Crush

free-llm launch crush

Cursor

Settings → Models → base URL

Cline

OpenAI Compatible provider

Roo Code

OpenAI Compatible provider

Kilo Code

OpenAI Compatible provider

Continue

config.yaml (chat + autocomplete)

Zed

Ollama or OpenAI-compatible

JetBrains AI

Ollama / OpenAI-compatible

Open WebUI

Connections → OpenAI API

LibreChat

custom endpoint

LobeChat

OpenAI provider

OpenAI SDK

base_url = …/v1

Anthropic SDK

base_url = router

LangChain

ChatOpenAI(base_url=…)

Vercel AI SDK

createOpenAI({ baseURL })

MCP clients

free models as a tool

Cursor calls custom endpoints from its own servers: run the router on a server, or expose it with a tunnel. All other tools work with the router on your own computer.

Tell it what you need

Send one of these as the model name — or any model id like deepseek-v4-flash, and the router finds a provider that serves it for free.

autoBest overall for each request
auto:codingStrongest coding models first — for agents
auto:fastLowest latency first — chat, autocomplete
auto:smartMost capable models first
auto:longLargest context windows first
auto:visionModels that can read images
auto:reasoningThinking / reasoning models first
auto:spreadRotate providers to stretch free quotas
auto:fusionAsk 3 different models, get one merged answer

Built for free tiers — the messy reality included

Instant failover

Rate limits, daily quotas, server errors, timeouts, empty answers, providers that go silent: it moves on before your app sees anything.

Learns as you use it

Measures each model's real speed and reliability, reads Retry-After and rate-limit headers, rotates several keys per provider.

Speaks every common API

OpenAI Chat & Responses (Codex), Anthropic Messages (Claude Code), Ollama, embeddings and an MCP server.

Fixes weak free models

Rescues tool calls written as text, hides <think> blocks, retries without unsupported parameters, handles provider quirks.

Same-day catalog, for everyone

Providers and models come live from free-llm.com and refresh on their own. No paid plan to get updates faster.

Private by design

Runs on your computer. Keys are AES-256-GCM encrypted and only sent to their own provider. No account, no telemetry.

Fusion mode

auto:fusion asks three different free models and merges the best answer — handy to double-check important work.

Tiny and dependency-free

About 100 KB, zero dependencies, Node.js 18+. Dashboard, CLI, background service, Docker.

Why not just…

One free key by handA paid AI gatewayFree-LLM Router
CostFreePay per tokenFree
When the free quota runs outYour tool stopsKeeps going (you pay)Switches to another free model
Free models availableOne provider'sMostly paid350+ from 66 providers
Claude Code / Codex on free modelsNeeds a translation proxyYes, with paid modelsOne command
New free modelsYou track them yourself—Arrive the same day
Where your keys liveYour machineTheir serversYour machine, encrypted

Questions

What is Free-LLM Router, in simple words?

A small program that runs on your computer and gives you one address that behaves like the OpenAI or Anthropic API. Behind that address it uses the free plans of many AI providers (Google Gemini, Groq, Mistral, OpenRouter, NVIDIA…) and always sends your request to a free model that is working right now. If one provider is busy or out of quota, it switches to the next one instantly, so your app or coding agent keeps working.

Is it really free?

Yes. The router is open source under the MIT license, with no paid tier, no account and no telemetry. The AI models are the providers' own free plans; the router never resells anything and never sees your traffic.

Do I need API keys?

Not to try: guest mode answers right away with a few no-account models (slow and limited). For real work, add 2 or 3 free keys — most providers give one in about a minute without a credit card — and you get dozens of fast, strong models.

Can I use Claude Code for free with it?

Yes. Run "free-llm setup claude" and Claude Code sends its requests to the router, which answers with free models (Opus is mapped to the most capable free models, Sonnet to the best coding models, Haiku to the fastest). Free models are very good but not identical to Claude: for the hardest tasks the quality can be lower.

Which tools work with it?

Anything that speaks the OpenAI or Anthropic API: Claude Code, Codex CLI, OpenCode, Aider, Qwen Code, Goose, Crush, Cursor, Cline, Roo Code, Kilo Code, Continue, Zed, JetBrains AI Assistant, Open WebUI, LibreChat, LobeChat, the OpenAI and Anthropic SDKs, LangChain, LlamaIndex, the Vercel AI SDK and MCP clients.

How does it stay up to date?

The list of free providers and models comes live from free-llm.com, where every free tier is checked against official sources. The router refreshes it automatically every few hours, so a new free model reaches every user the same day — no paid plan, no delay.

Where are my API keys stored?

Only on your computer, in ~/.free-llm, encrypted with AES-256-GCM. Requests go directly from your machine to each provider.

Is it allowed by the providers?

The router only uses your own keys, at your request, like any client app would. Each free plan has its own terms (personal use, rate limits, data use), so read the terms of the providers you sign up for.

Stop hitting free-tier walls

One minute to install. Free forever. Open source.

Know a free provider we're missing? Submit it — once checked, it reaches every router the same day.